Qwen 3.8-Max Now on Modal: 2.4T Params, 1M Context, Custom DFlash Speculator
AAAzzam · x · 2026-08-14
Alibaba's Qwen 3.8-Max is now available on Modal, with full 1M context window and a custom DFlash speculator trained on tool-call-heavy data. The model has 2.4T parameters (95B active) and is a Modal call away.
Related event: Alibaba's Qwen3.8-Max Lands on Five Hosted Platforms with Open Weights(6 posts)→
More from Infra
- Three CoreWeave co-founders have sold $3.3B in shares since IPO amid credit worries — SumitGup · 2026-10-16
- Cherry pi on a Raspberry Pi: the tiny-model rumor developers are watching — sull · 2026-10-16
- CoreWeave's debt costs falling: DDTL spreads tightened from S+9.62% to S+2.25% — BenBajarin · 2026-10-16
- SoftBank lines up US IPOs for SB Energy and AI robotics spinoff Roze, valuations top $50B — nordicinst · 2026-10-16
- TRL reproduces Modal's mixed-precision async RL: plain GRPO collapses, SC+MIS holds 0.72 — QGallouedec · 2026-10-16
- Hugging Face scales Indic pretraining with 2.8T tokens and an open data pipeline — Hugging Face Blog · 2026-10-16